Data Cleaning Pipeline

Build a pandas pipeline that imputes missing values, removes duplicates, caps IQR outliers, standardizes data types, and scales numeric features. This yields an analysis-ready dataset and a before/after quality metrics report for reliable preprocessing.

Apply IQR-based bounds to detect and cap outliers in numeric columns, and impute missing values using median or KNN rules. This removes noisy records and standardizes inconsistent formatting for reliable downstream analysis.

Generate a data quality report by running integrity checks that output before/after metrics on rows removed and remaining missingness. This validates that deterministic cleaning steps successfully repaired inconsistent formatting and noisy records.

This approach suits automated data quality pipelines by enforcing type conversions, cleaning text fields, and applying deterministic imputation. It standardizes inconsistent formatting and noisy records to ensure reliable inputs for downstream analysis.

Standardize data types by enforcing datetime conversions and cleaning text fields to repair inconsistent formatting. This yields analysis-ready data that ensures downstream analysis and modeling run reliably without type errors.